Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    relevant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    缇
    -0.08
    _Msp
    -0.07
    �
    -0.07
    桑
    -0.07
    ڹ
    -0.07
    蒯
    -0.07
    бур
    -0.07
    �
    -0.07
    ศาส
    -0.07
    郫
    -0.06
    POSITIVE LOGITS
     comparable
    0.07
    BOSE
    0.07
    ((_
    0.07
     Louise
    0.07
     Lonely
    0.06
    label
    0.06
     Rookie
    0.06
    牵挂
    0.06
     KK
    0.06
     Co
    0.06
    Act Density 0.025%

    No Known Activations